Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add darthzen/fossa-mcp --skill fossa-suggest-scoregit clone --depth 1 https://github.com/darthzen/fossa-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/darthzen/fossa-mcp/fossa-suggest-score)<a href="https://agentmods.dev/skills/darthzen/fossa-mcp/fossa-suggest-score"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-suggest-score/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/darthzen/fossa-mcp/fossa-suggest-score"><img src="https://agentmods.dev/badge/skills/darthzen/fossa-mcp/fossa-suggest-score.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.04737 |
| Opus 5 | $0.00042 | $0.02368 |
| Sonnet 5 | $0.00017 | $0.00947 |
| Haiku 4.5 | $0.00008 | $0.00474 |
Grade C, and why
fossa-suggest-score scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
delta.** Do not silently assume, and do not refuse to score. How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fossa-suggest-score
Read a FOSSA org's open issues, score every finding on a rubric that CVSS alone cannot express, roll the findings up per project, and hand back a ranked remediation list plus the version bumps that actually clear it.
Why this workflow exists: CVSS ranks the vulnerability. It does not know whether the vulnerable code path is compiled into your binary, whether the service listens on a network, or whether the package is a test-only dependency. In a real portfolio those three facts move findings by 25–30 points and reorder the list. The score below is CVSS and EPSS — both straight out of FOSSA — plus three judgment terms that you must gather and must label as judgment.
The honest framing, stated up front and never dropped: the reachability and exposure terms are your assessment, not FOSSA data. They carry 35% of the weight between them. Every report states the assumption explicitly, and states what the ranking becomes if the assumption is wrong. A score presented as if it came out of FOSSA is worse than no score.
Ask which org or project set if it isn't obvious. Everything else is procedure.
1. Inventory
fossa_list_projects(count=50, sort="issues-total_desc")
That one call gives you titles, locators, latestRevision.locator, per-category
issue counts, and public. Projects with issues.total == 0 need no
remediation — name them as clean and drop them; do not spend calls on them.
Never guess a locator from a repo name. If the user named projects informally,
resolve each with fossa_list_projects(title=...) first — but title is a
substring match that can return several projects, not a lookup. Read the
result before picking; if more than one comes back, disambiguate with the user
rather than taking the first row.
Deduplicate the inventory before scoring it. One repository can appear as
several FOSSA projects — a CLI/integration scan under git+<host>/<org>/<repo>
and a separately uploaded scan of the same tree under
custom+<orgId>/<something>, each with its own title. Observed live: two
projects at the same commit SHA, returning the same issue ids, with
issue counts that differ only because the two scans included different dev
dependencies. Scoring both puts one codebase in the ranking twice and
double-counts the portfolio's remediation work.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 365 lines · 84 tokens per session scan C 7fa1ad5c33b9
fossa-suggest-score is a skill published in the GitHub repository darthzen/fossa-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 4,737 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…